SyslogSolution/ra-h-os
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

cleanup(skills): remove legacy guide bundle and harden skill migration/pruning

Browse Source
This commit is contained in:
“BeeRad”
2026-03-07 12:00:52 +11:00
parent b67a789740
commit bc226b03c8
16 changed files with 134 additions and 581 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/config/guides/connect.md
-42
View File
@@ -1,42 +0,0 @@
---
name: Connect
description: Quick link — find explicitly related nodes and create edges between them.
---
# Connect
Quick link: find explicitly related nodes and create edges.
## Steps
1. **Read Node**
Call `getNodesById` for the focused node. Extract the main topic/subject from the title.
2. **Quick Search**
Call `queryNodes` with the main topic from the node title.
- `search`: the key term from the title (e.g., if title mentions "Nietzsche", search "Nietzsche")
- `limit`: 10
- Do NOT add dimensions filter — search across all nodes
3. **Create Edges**
From results, pick 2-4 clearly related nodes.
Call `createEdge` for each:
- `from_node_id`: focused node ID
- `to_node_id`: related node ID
- `explanation`: "brief reason for this connection"
Direction rule: write the explanation so it reads FROM → TO.
Examples:
- Episode → Podcast: "Episode of this podcast"
- Book → Author: "Written by"
4. **Done**
Reply: "Linked [NODE:id:title] → [list of connected nodes as NODE:id:title]"
## Rules
- Total tool calls ≤ 5
- Search the MAIN TOPIC from the title, not random names from content
- NO dimensions filter in `queryNodes` — search everything
- Only link nodes with clear relationships
- Skip if no matches found
src/config/guides/integrate.md
-71
View File
@@ -1,71 +0,0 @@
---
name: Integrate
description: Full analysis — find connections across the knowledge graph, create edges, and document an integration analysis.
---
# Integrate
Find meaningful connections across the knowledge graph, create edges, and append an Integration Analysis.
## Steps
1. **Retrieve & Understand**
- Call `getNodesById` for the focused node
- Identify: what type of thing is this? (person, project, paper, idea, video, etc.)
- Extract key entities: names, projects, concepts, techniques
- Note the core insight in one sentence
2. **Search for Connections**
Search the database using entities from step 1:
a) Structural connections:
- Names mentioned → `queryNodes` to find nodes about those people
- Projects/tools mentioned → `queryNodes` to find those nodes
b) Thematic connections:
- Use `searchContentEmbeddings` with key concepts
- Look for shared themes, complementary ideas, contradictions
Target: 3-5 strong connections (quality over quantity)
3. **Create Edges**
For each connection found, call `createEdge`:
- `from_node_id`: the focused node ID
- `to_node_id`: the connected node ID
- `explanation`: "why this connection matters"
Direction rule: write the explanation so it reads FROM → TO.
Examples:
- Insight → Source: "Came from / inspired by"
- Episode → Podcast: "Episode of this podcast"
The tool handles duplicates gracefully — if edge exists, it returns an error and you continue.
Create 3-5 edges total.
4. **Document in Content**
Call `updateNode` ONCE using the `content` field with ONLY this new section:
```
---
## Integration Analysis
[2-3 sentences: what this is, why it matters, core insight]
**Connections:**
- [NODE:123:"Title"] — [why connected]
- [NODE:456:"Title"] — [why connected]
```
Use `updates.content` (NOT chunk). Send ONLY the new section. The tool appends automatically.
5. **Return Summary**
Reply with: Task / Actions / Result / Nodes / Follow-up (≤100 words)
## Rules
- Keep total tool calls ≤ 12
- Create edges BEFORE documenting (step 3 before step 4)
- Call `updateNode` exactly once
- Adapt to any node type
- Use `think` at any point if you need to plan your approach
src/config/guides/preferences.md
-14
View File
@@ -1,14 +0,0 @@
---
name: Preferences
description: Your communication style, workflow rules, and current priorities.
---
# Preferences
Add your preferences here. The agent will read this guide to understand how you like to work.
## Examples of what to put here
- Communication style (bullet points vs prose, level of detail)
- Workflow rules (always ask before creating dimensions, etc.)
- Current priorities (what you're focused on this week)
- Timezone and locale
src/config/guides/prep.md
-39
View File
@@ -1,39 +0,0 @@
---
name: Prep
description: Quick summary brief — extract the gist to help decide if content is worth deeper engagement.
---
# Prep
Quick summary to help the user decide if content is worth deeper engagement.
## Steps
1. **Read the Node**
- Call `getNodesById` for the focused node
- Understand what this is and extract the core message
2. **Append Brief**
Call `updateNode` ONCE using the `content` field with ONLY this section:
```
---
## Brief
**What:** [One sentence — what is this?]
**Gist:** [2-3 sentences — the core message or takeaway]
**Why it matters:** [1-2 sentences — relevance or implications]
```
Use `updates.content` (NOT chunk). Send ONLY the new section. The tool appends automatically.
3. **Return Summary**
Reply with a one-line confirmation: "Prepped [title] — [gist in <10 words]"
## Rules
- Keep total tool calls ≤ 3
- Call `updateNode` exactly once
- Be concise — this is a quick prep, not deep analysis
src/config/guides/research.md
-48
View File
@@ -1,48 +0,0 @@
---
name: Research
description: Deep research — conduct background web research on a topic and append findings to the node.
---
# Research
Conduct background research on the topic/person/concept and append findings to the node.
## Steps
1. **Read & Identify**
- Call `getNodesById` for the focused node
- Identify: what needs researching? (person's background, concept origins, recent developments, etc.)
2. **Web Research**
- Call `webSearch` with targeted queries (1-2 searches)
- Focus on: background context, recent news, authoritative sources
- Extract the most relevant findings
3. **Append Research**
Call `updateNode` ONCE using the `content` field with ONLY this section:
```
---
## Research Notes
**Background:** [2-3 sentences of context]
**Key Findings:**
- [Finding 1]
- [Finding 2]
- [Finding 3]
**Sources:** [Brief attribution]
```
Use `updates.content` (NOT chunk). Send ONLY the new section. The tool appends automatically.
4. **Return Summary**
Reply with: "Researched [topic] — [key insight in <15 words]"
## Rules
- Keep total tool calls ≤ 5
- Call `updateNode` exactly once
- Focus on factual background, not opinion
- Cite sources when possible
src/config/guides/survey.md
-53
View File
@@ -1,53 +0,0 @@
---
name: Survey
description: Survey a dimension — analyze patterns, themes, gaps, and insights across all nodes within it.
---
# Survey
Analyze the active dimension to identify patterns, themes, gaps, and insights across all nodes within it.
**Prerequisite:** This guide requires an active dimension. Check the ACTIVE DIMENSION section in context.
## Steps
1. **Retrieve Dimension Nodes**
- Call `queryDimensionNodes` with the active dimension name
- Set limit to 50 to get a comprehensive view
- Note the total count and most connected nodes
2. **Analyze Themes**
- Call `searchContentEmbeddings` with key concepts from the dimension
- Identify recurring themes, patterns, and relationships
- Note any gaps or underrepresented areas
3. **Document Findings**
Call `updateDimension` to update the dimension description with:
```
**Survey Summary**
**Node Count:** [X nodes]
**Top Hubs:** [List 3-5 most connected nodes with [NODE:id:"title"]]
**Themes:**
- [Theme 1 — brief description]
- [Theme 2 — brief description]
**Gaps/Opportunities:**
- [Identified gap or area for expansion]
**Connections to Other Dimensions:**
- [Any cross-dimension patterns observed]
```
4. **Return Summary**
Reply with: "Surveyed [dimension] — [X nodes, key insight in <15 words]"
## Rules
- Keep total tool calls ≤ 5
- Focus on patterns across the dimension, not individual node details
- Identify both strengths (dense areas) and gaps (sparse areas)
- Reference specific nodes using `[NODE:id:"title"]` format
- If no active dimension is set, inform the user to open a dimension folder first
src/config/guides/system/creating-nodes.md
-48
View File
@@ -1,48 +0,0 @@
---
name: Creating Nodes
description: When and how to create nodes. Link field rules. Synthesis patterns.
immutable: true
---
# Creating Nodes
## When to Create
- User explicitly asks to save/capture something
- Extracting insights from existing content (synthesis)
- Ingesting external content (YouTube, website, PDF)
## Link Field Rules
- **Has link:** Node directly represents external content (YouTube video, website, PDF, article)
- **No link:** Node is derived/synthesized from existing content (ideas, insights, summaries, questions)
- Never add a link to synthesis or idea nodes
## Synthesis Pattern
When creating a node derived from existing content:
1. Create the node WITHOUT a link field
2. Call `createEdge` to connect it to ALL source nodes
3. Each edge needs an explanation ("Insight extracted from...", "Synthesized from...")
## Dimension Assignment
- New nodes should be assigned to relevant existing dimensions
- Check priority dimensions — assign these when relevant
- If no existing dimension fits, create a new one (but prefer existing)
## Description Field
The description is the most important field for AI context. It powers search (5x boost),
appears in system prompts, and determines how agents understand the node.
**Standard:** State WHAT this is + WHY it matters. Extremely concise, high-level. Max 280 characters.
**Rules:**
- NO weak verbs: "discusses", "explores", "examines", "talks about"
- State the actual claim, insight, or purpose directly
- Include significance or implication in 1 phrase
- If auto-generated (omitted), the system will generate one — but agent-written descriptions are always better
**Good:** "By Karpathy — Software is becoming fluid: agents can rip functionality from repos instead of taking dependencies."
**Bad:** "This article discusses the importance of software becoming more fluid."
src/config/guides/system/dimensions.md
-38
View File
@@ -1,38 +0,0 @@
---
name: Dimensions
description: Create, lock, describe, organize, clean up dimensions.
immutable: true
---
# Dimensions
Dimensions are how nodes are categorized and organized. Think of them as flexible tags with descriptions.
## Operations
- **Create:** `createDimension(name, description, isPriority)`
- **Update:** `updateDimension(name, { newName, description, isPriority })`
- **Delete:** `deleteDimension(name)` — removes from all nodes
- **Query:** Use sqliteQuery to list dimensions and their node counts
## Locking (Priority)
- `isPriority = true` (locked) → dimension auto-assigns to new nodes when relevant
- `isPriority = false` (unlocked) → manual assignment only
- Lock dimensions that represent active areas of focus
## Naming Conventions
- Lowercase, concise (e.g., "ai", "philosophy", "ra-h")
- Use singular form where natural
- Avoid overlapping names (don't have both "ai" and "artificial-intelligence")
## Description
Every dimension should have a description explaining its purpose. This helps the AI correctly assign nodes to dimensions.
## Cleanup
- Delete dimensions with 0 nodes
- Merge overlapping dimensions (update nodes, then delete the redundant one)
- Regularly review dimension list for coherence
src/config/guides/system/edges.md
-51
View File
@@ -1,51 +0,0 @@
---
name: Edges
description: Edge philosophy. Explanations, direction, types. Connection patterns.
immutable: true
---
# Edges
## Philosophy
Edges are the most valuable part of the knowledge graph. Individual nodes are useful; the web of connections between them is what makes the graph powerful.
## Rules
1. **Every edge needs an explanation** — why does this connection exist? Be specific.
2. **Direction matters** — FROM → TO should read like a sentence
3. **Types are inferred** — the system infers category/type from your explanation. Don't set types manually.
## Direction Convention
Write the explanation so FROM → TO reads naturally:
- Episode → Podcast: "Episode of this podcast"
- Book → Author: "Written by this author"
- Insight → Source: "Extracted from this source"
- Idea → Related idea: "Builds on this concept"
## Edge Context JSON
```json
{
"explanation": "Human-readable reason",
"category": "inferred (created_by, features, part_of, source_of, related_to)",
"type": "inferred specific type",
"confidence": 0.0-1.0,
"created_via": "chat|mcp|workflow"
}
```
## Hub Traversal
Hub nodes (most-connected) are the user's core themes. To understand context around a topic:
1. Find the relevant hub node
2. Use `queryEdge` or sqliteQuery to get its connections
3. Traverse outward to related nodes
## When to Create Edges
- After creating synthesis/idea nodes (connect to sources)
- When user mentions a relationship between topics
- When running the Connect or Integrate guides
- When obvious connections exist that aren't captured
src/config/guides/system/extract.md
-33
View File
@@ -1,33 +0,0 @@
---
name: Extract
description: Extraction pre-check. When to reuse chunks vs re-extract.
immutable: true
---
# Content Extraction
## Pre-Check (REQUIRED)
Before running any extraction tool, always check the node first:
1. Call `getNodesById` on the target node
2. Check `chunk_status`:
- **'chunked'** → content already extracted. Reuse existing chunks. Do NOT re-extract.
- **'pending'** or missing → safe to extract
- **'failed'** → previous extraction failed, safe to retry
3. Check if embeddings are available (chunk length > 0)
- If available, use `searchContentEmbeddings` instead of re-extracting
## Extraction Tools
- **youtubeExtract** — YouTube videos (requires URL with video ID)
- **websiteExtract** — Web pages (uses Jina.ai for JS-rendered sites)
- **paperExtract** — PDF files (requires direct PDF URL)
## After Extraction
- The extracted content goes into `chunk` (full source)
- AI generates a `description` (grounding summary)
- Embeddings are created automatically
- Assign to relevant dimensions
src/config/guides/system/schema.md
-111
View File
@@ -1,111 +0,0 @@
---
name: Schema
description: Full database schema, tables, columns, query patterns.
immutable: true
---
# Database Schema
## Tables
### nodes
| Column | Type | Notes |
|--------|------|-------|
| id | INTEGER | Primary key, auto-increment |
| title | TEXT | Required |
| description | TEXT | AI-generated grounding context (~1 sentence) |
| notes | TEXT | User's notes/thoughts (not source content) |
| chunk | TEXT | Full verbatim source content |
| chunk_status | TEXT | 'pending', 'chunked', 'failed' |
| link | TEXT | External URL (only for nodes representing external content) |
| event_date | TEXT | When the content happened (ISO date) — distinct from created_at |
| metadata | TEXT | JSON blob (map_position, transcript_length, etc.) |
| created_at | TEXT | ISO timestamp |
| updated_at | TEXT | ISO timestamp |
### edges
| Column | Type | Notes |
|--------|------|-------|
| id | INTEGER | Primary key |
| from_node_id | INTEGER | FK → nodes.id |
| to_node_id | INTEGER | FK → nodes.id |
| context | TEXT | JSON: `{ explanation, category, type, confidence, created_via }` |
| source | TEXT | 'user', 'ai_similarity', or helper name |
| explanation | TEXT | Human-readable reason for connection |
| created_at | TEXT | ISO timestamp |
### dimensions
| Column | Type | Notes |
|--------|------|-------|
| name | TEXT | Primary key |
| description | TEXT | Purpose description |
| icon | TEXT | Emoji or icon identifier for UI display |
| is_priority | INTEGER | 1 = priority dimension (auto-assigns to new nodes) |
| updated_at | TEXT | ISO timestamp |
### node_dimensions (junction)
| Column | Type |
|--------|------|
| node_id | INTEGER FK → nodes.id |
| dimension | TEXT (dimension name) |
### chunks (for semantic search)
| Column | Type | Notes |
|--------|------|-------|
| id | INTEGER | Primary key |
| node_id | INTEGER | FK → nodes.id |
| chunk_idx | INTEGER | Position in sequence |
| text | TEXT | Chunk content |
| created_at | TEXT | ISO timestamp |
| embedding_type | TEXT | Embedding model used |
| metadata | TEXT | JSON blob |
### voice_usage (daily tracking)
| Column | Type | Notes |
|--------|------|-------|
| id | INTEGER | Primary key |
| date | TEXT | ISO date (UNIQUE) |
| minutes_used | REAL | Minutes consumed |
| updated_at | TEXT | ISO timestamp |
### FTS Tables
- `chunks_fts` — full-text search on chunk text
- `nodes_fts` — full-text search on node title + notes
## Common Query Patterns
**Top connected nodes (hubs):**
```sql
SELECT n.id, n.title, n.description, COUNT(DISTINCT e.id) AS edge_count
FROM nodes n
LEFT JOIN edges e ON (e.from_node_id = n.id OR e.to_node_id = n.id)
GROUP BY n.id ORDER BY edge_count DESC LIMIT 5
```
**Nodes in a dimension:**
```sql
SELECT n.* FROM nodes n
JOIN node_dimensions nd ON n.id = nd.node_id
WHERE nd.dimension = ?
```
**Edges for a node (both directions):**
```sql
SELECT e.*, n1.title as from_title, n2.title as to_title
FROM edges e
JOIN nodes n1 ON e.from_node_id = n1.id
JOIN nodes n2 ON e.to_node_id = n2.id
WHERE e.from_node_id = ? OR e.to_node_id = ?
```
**Search source content (chunks):**
```sql
SELECT c.id, c.node_id, c.chunk_idx, c.text, n.title
FROM chunks c
JOIN nodes n ON c.node_id = n.id
WHERE c.text LIKE '%search term%' COLLATE NOCASE
ORDER BY c.chunk_idx ASC
LIMIT 10
```
**Use `rah_search_content` to search chunks by keyword, or `rah_sqlite_query` for any read operation not covered by structured tools.**